| { |
| "architectures": [ |
| "FalconH1MoEForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attention_in_multiplier": 1.0, |
| "attention_out_multiplier": 0.234375, |
| "attn_layer_indices": null, |
| "auto_map": { |
| "AutoConfig": "configuration_falcon_h1_moe.FalconH1MoEConfig", |
| "AutoModel": "modeling_falcon_h1_moe.FalconH1MoEForCausalLM" |
| }, |
| "bos_token_id": 1, |
| "embedding_multiplier": 5.656854249492381, |
| "eos_token_id": 11, |
| "expert_num": 4, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "intermediate_size": 4608, |
| "key_multiplier": 0.06905339660024876, |
| "lm_head_multiplier": 0.01953125, |
| "mamba_chunk_size": 128, |
| "mamba_conv_bias": true, |
| "mamba_d_conv": 4, |
| "mamba_d_head": 64, |
| "mamba_d_ssm": 3072, |
| "mamba_d_state": 256, |
| "mamba_expand": 2, |
| "mamba_n_groups": 1, |
| "mamba_n_heads": 48, |
| "mamba_norm_before_gate": false, |
| "mamba_proj_bias": false, |
| "mamba_rms_norm": true, |
| "mamba_use_mlp": true, |
| "max_position_embeddings": 131072, |
| "mlp_bias": false, |
| "mlp_expansion_factor": 8, |
| "mlp_multipliers": [ |
| 0.4419417382415922, |
| 0.13020833333333331 |
| ], |
| "model_type": "falcon_h1", |
| "num_attention_heads": 8, |
| "num_hidden_layers": 24, |
| "num_key_value_heads": 2, |
| "num_logits_to_keep": 1, |
| "pad_token_id": 0, |
| "projectors_bias": false, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 100000000000.0, |
| "ssm_in_multiplier": 0.625, |
| "ssm_multipliers": [ |
| 0.3535533905932738, |
| 0.25, |
| 0.1767766952966369, |
| 0.5, |
| 0.3535533905932738 |
| ], |
| "ssm_out_multiplier": 0.11785113019775793, |
| "tie_word_embeddings": false, |
| "topk": 2, |
| "torch_dtype": "float32", |
| "transformers_version": "4.55.2", |
| "use_cache": true, |
| "vocab_size": 65536 |
| } |
|
|